# jina

**Repository Path**: lilujunai/jina

## Basic Information

- **Project Name**: jina
- **Description**: Jina is the cloud-native neural search framework powered by state-of-the-art AI and deep learning
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 1
- **Created**: 2020-08-22
- **Last Updated**: 2025-04-17

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

<p align="center">
  <img src="https://github.com/jina-ai/jina/blob/master/.github/1500х667.gif?raw=true" alt="Jina banner" width="100%">
</p>

<p align="center">
 
[![Jina](https://github.com/jina-ai/jina/blob/master/.github/badges/jina-badge.svg?raw=true  "We fully commit to open-source")](https://jina.ai)
[![Jina](https://github.com/jina-ai/jina/blob/master/.github/badges/jina-hello-world-badge.svg?raw=true  "Run Jina 'Hello, World!' without installing anything")](#jina-hello-world-)
[![Jina](https://github.com/jina-ai/jina/blob/master/.github/badges/license-badge.svg?raw=true  "Jina is licensed under Apache-2.0")](#license)
[![Jina Docs](https://github.com/jina-ai/jina/blob/master/.github/badges/docs-badge.svg?raw=true  "Checkout our docs and learn Jina")](https://docs.jina.ai)
[![We are hiring](https://github.com/jina-ai/jina/blob/master/.github/badges/jina-corp-badge-hiring.svg?raw=true  "We are hiring full-time position at Jina")](https://jobs.jina.ai)
<a href="https://twitter.com/intent/tweet?text=%F0%9F%91%8DCheck+out+Jina%3A+the+New+Open-Source+Solution+for+Neural+Information+Retrieval+%F0%9F%94%8D%40JinaAI_&url=https%3A%2F%2Fgithub.com%2Fjina-ai%2Fjina&hashtags=JinaSearch&original_referer=http%3A%2F%2Fgithub.com%2F&tw_p=tweetbutton" target="_blank">
  <img src="https://github.com/jina-ai/jina/blob/master/.github/badges/twitter-badge.svg?raw=true "
       alt="tweet button" title="👍Share Jina with your friends on Twitter"></img>
</a>
[![Python 3.7 3.8](https://github.com/jina-ai/jina/blob/master/.github/badges/python-badge.svg?raw=true  "Jina supports Python 3.7 and above")](https://pypi.org/project/jina/)
[![PyPI](https://img.shields.io/pypi/v/jina?color=%23099cec&label=PyPI%20package&logo=pypi&logoColor=white)]()
[![Docker](https://github.com/jina-ai/jina/blob/master/.github/badges/docker-badge.svg?raw=true  "Jina is multi-arch ready, can run on different architectures")](https://hub.docker.com/r/jinaai/jina/tags)
[![Docker Image Version (latest semver)](https://img.shields.io/docker/v/jinaai/jina?color=%23099cec&label=Docker%20Image&logo=docker&logoColor=white&sort=semver)](https://hub.docker.com/r/jinaai/jina/tags)
[![CI](https://github.com/jina-ai/jina/workflows/CI/badge.svg)](https://github.com/jina-ai/jina/actions?query=workflow%3ACI)
[![CD](https://github.com/jina-ai/jina/workflows/CD/badge.svg?branch=master)](https://github.com/jina-ai/jina/actions?query=workflow%3ACD)
[![Release Cycle](https://github.com/jina-ai/jina/workflows/Release%20Cycle/badge.svg)](https://github.com/jina-ai/jina/actions?query=workflow%3A%22Release+Cycle%22)
[![Release CD](https://github.com/jina-ai/jina/workflows/Release%20CD/badge.svg)](https://github.com/jina-ai/jina/actions?query=workflow%3A%22Release+CD%22)

</p>

<p align="center">
  <a href="https://github.com/jina-ai/jina">English</a> •
  <a href="https://github.com/jina-ai/jina/blob/master/README.ja.md">日本語</a> •
  <a href="https://github.com/jina-ai/jina/blob/master/README.fr.md">français</a> •
  <a href="https://github.com/jina-ai/jina/blob/master/README.de.md">Deutsch</a> •
  <a href="https://github.com/jina-ai/jina/blob/master/README.ru.md">Русский язык</a> •
  <a href="https://github.com/jina-ai/jina/blob/master/README.zh.md">中文</a>
</p>

<p align="center">
  <a href="https://jina.ai">Website</a> •
  <a href="https://docs.jina.ai">Docs</a> •
  <a href="https://learn.jina.ai">Examples</a> •
  <a href="mailto:newsletter+subscribe@jina.ai">Newsletter</a> •
  <a href="https://github.com/jina-ai/jina-hub">Hub (beta)</a> •
  <a href="https://dashboard.jina.ai">Dashboard (beta)</a> •
  <a href="https://twitter.com/intent/tweet?text=%F0%9F%91%8DCheck+out+Jina%3A+the+New+Open-Source+Solution+for+Neural+Information+Retrieval+%F0%9F%94%8D%40JinaAI_&url=https%3A%2F%2Fgithub.com%2Fjina-ai%2Fjina&hashtags=JinaSearch&original_referer=http%3A%2F%2Fgithub.com%2F&tw_p=tweetbutton">Twitter</a> •
  <a href="https://jobs.jina.ai">We are Hiring</a>

</p>

想建立一个以深度学习为支撑的搜索系统？你来对地方了!

Jina是由最先进的AI和深度学习驱动的云端神经搜索框架。它得到了一个全职的、由风险投资支持的团队的长期支持。

🌌**通用搜索解决方案** - Jina可以在多个平台和架构上实现任何类型的大规模索引和查询。无论您是搜索图片、视频片段、音频片段、长的法律文档、短的推文，Jina都能处理。

🚀**高性能和最先进的设备** - Jina的目标是AI在生产过程中。你可以轻松地扩展出你的VideoBERT、Xception、你的单词令牌器、图像分割器和数据库来处理亿级数据。复制品和碎片等功能都是现成的。

🐣**简单的系统工程** - Jina提供了一个一站式的解决方案，让你从手工制作和粘合包、库和数据库中解脱出来。通过最直观的API和[仪表板](https://github.com/jina-ai/dashboard)构建一个云端搜索系统只是分分钟的事情。

🧩**强大的扩展功能，简单的集成** - Jina的新AI模型？只需编写一个Python脚本或构建一个Docker镜像即可。插入新的算法从来都不是那么容易的事情，就像它应该做的那样。[看看Jina Hub (测试版)](https://github.com/jina-ai/jina-hub)并在社区贡献的不同用例上找到更多的扩展。

Jina是一个开源项目。[我们正在招聘](https://jobs.jina.ai)AI工程师、全栈开发者、传道者、PM，打造下一个开源的神经搜索生态。

## 目录

<img align="right" width="350px" src="https://github.com/jina-ai/jina/blob/master/.github/install.png?raw=true " />

<!-- START doctoc generated TOC please keep comment here to allow auto update -->
<!-- DON'T EDIT THIS SECTION, INSTEAD RE-RUN doctoc TO UPDATE -->


- [安装](#%E5%AE%89%E8%A3%85)
- [Jina "你好，世界！"👋🌍](#jina-%E4%BD%A0%E5%A5%BD%E4%B8%96%E7%95%8C)
- [开始](#%E5%BC%80%E5%A7%8B)
- [文档](#%E6%96%87%E6%A1%A3)
- [贡献者](#%E8%B4%A1%E7%8C%AE%E8%80%85)
- [社区](#%E7%A4%BE%E5%8C%BA)
- [路线图](#%E8%B7%AF%E7%BA%BF%E5%9B%BE)
- [许可证](#%E8%AE%B8%E5%8F%AF%E8%AF%81)

<!-- END doctoc generated TOC please keep comment here to allow auto update -->

## 安装

#### 从PyPi安装

在安装了 Python >= 3.7 的 Linux/MacOS 上，只需在终端上运行此命令即可。

```bash
pip install jina
```

要在Raspberry Pi上安装Jina，或者在Raspberry Pi上安装Jina，需要额外的依赖关系。[请参考文件](https://docs.jina.ai).

#### ...或使用Docker容器运行

我们提供了一个通用的Docker图像（只有80MB！），支持多种架构（包括x64、x86、x86、arm-64/v7/v6），只需做到这一点。

```bash
docker run jinaai/jina
```

## Jina "你好，世界！"👋🌍

作为入门者，我们邀请你尝试一下Jina的 "Hello，世界"--简单的图像神经搜索的演示[Fashion-MNIST](https://hanxiao.io/2018/09/28/Fashion-MNIST-Year-In-Review/).不需要额外的依赖关系，只需做。

```bash
jina hello-world
```

....甚至对Docker用户来说更容易。**不需要任何安装**。简单地。

```bash
docker run -v "$(PWD)/j:/j" jinaai/jina hello-world --workdir /j && open j/hello-world.html
```

<details>
<summary>Click here to see the console output</summary>

<p align="center">
  <img src="https://github.com/jina-ai/jina/blob/master/docs/chapters/helloworld/hello-world-demo.png?raw=true" alt="hello world console output">
</p>

</details>  

它下载Fashi-MNIST训练和测试数据；告诉Jina从训练集中索引6万张图像。然后，它从测试集中随机抽取图像作为查询，要求Jina检索相关结果。大约1分钟后，它将打开一个网页，并显示出这样的结果。

<p align="center">
  <img src="https://github.com/jina-ai/jina/blob/master/docs/chapters/helloworld/hello-world.gif?raw=true" alt="Jina banner" width="90%">
</p>

那背后的实施呢？就像它应该是很简单的。

<table>
<tr>
<td> Python API </td>
<td> index.yml</td>
<td> <a href="https://github.com/jina-ai/dashboard">Flow in Dashboard</a></td>
</tr>
<tr>
<td> 

```python
from jina.flow import Flow

f = Flow.load_config('index.yml')

with f:
    f.index(raw_bytes=input_fn)
```

</td>
<td>
  <sub>

```yaml
!Flow
pods:
  chunk_seg:
    yaml_path: helloworld.crafter.yml
    replicas: $REPLICAS
    read_only: true
  doc_idx:
    yaml_path: helloworld.indexer.doc.yml
  encode:
    yaml_path: helloworld.encoder.yml
    needs: chunk_seg
    replicas: $REPLICAS
  chunk_idx:
    yaml_path: helloworld.indexer.chunk.yml
    replicas: $SHARDS
    separated_workspace: true
  join_all:
    yaml_path: _merge
    needs: [doc_idx, chunk_idx]
    read_only: true
```

</sub>

</td>
<td>

![Flow in Dashboard](https://github.com/jina-ai/jina/blob/master/docs/chapters/helloworld/hello-world-flow.png?raw=true)

</td>
</tr>
</table>

所有你能说出名字的大词：计算机视觉、神经IR、微服务、消息队列、弹性、复制&碎片，都是在短短一分钟内发生的!

有兴趣吗？玩，并尝试不同的选择。

```bash
jina hello-world --help
```

[请务必继续关注我们的《Jina101指南》。](https://github.com/jina-ai/jina#jina-101-first-thing-to-learn-about-jina) - 在3分钟内理解Jina的所有关键概念!  

## 开始

<table>
  <tr>
      <td width="30%">
    <a href="https://github.com/jina-ai/jina/tree/master/docs/chapters/101">
      <img src="https://github.com/jina-ai/jina/blob/master/docs/chapters/101/img/ILLUS12.png?raw=true" alt="Jina 101 Concept Illustration Book, Copyright by Jina AI Limited" title="Jina 101 Concept Illustration Book, Copyright by Jina AI Limited"/>
    </a>
    </td>
    <td width="70%">
&nbsp;&nbsp;<h3><a href="https://github.com/jina-ai/jina/tree/master/docs/chapters/101">Jina 101: First Thing to Learn About Jina</a></h3>
&nbsp;&nbsp;<a href="https://github.com/jina-ai/jina/tree/master/docs/chapters/101">English</a> •
  <a href="https://github.com/jina-ai/jina/tree/master/docs/chapters/101/README.jp.md">日本語</a> •
  <a href="https://github.com/jina-ai/jina/tree/master/docs/chapters/101/README.fr.md">français</a> •
  <a href="https://github.com/jina-ai/jina/tree/master/docs/chapters/101/README.ru.md">Русский язык</a> •
  <a href="https://github.com/jina-ai/jina/tree/master/docs/chapters/101/README.cn.md">中文</a>
    </td>

  </tr>
</table>

<table>
<tr><th width="90%">Tutorials</th><th width="10%">Level</th></tr><tr>

<tr>
<td>
<h4><a href="https://docs.jina.ai/chapters/flow/README.html">Use Flow API to Compose Your Search Workflow</a></h4>
Learn how to orchestrate Pods to work together: sequentially and in parallel; locally and remotely
</td>
<td><h3>🐣</h3></td>
</tr>

<tr>
<td>
<h4><a href="https://github.com/jina-ai/dashboard">Use Dashboard to Get Insight of Jina Workflow</a></h4>
Learn to use dashboard to monitor and get insight of a running workflow
</td>
<td><h3>🐣</h3></td>
</tr>

<tr>
<td>
<h4><a href="https://github.com/jina-ai/examples/tree/master/x-as-service">From BERT-as-Service to X-as-Service</a></h4>
Learn how to use Jina to extract feature vector using any deep learning representation
</td>
<td><h3>🐣</h3></td>
</tr>

<tr>
<td>
<h4><a href="https://github.com/jina-ai/examples/tree/master/southpark-search">Build a NLP Semantic Search System</a></h4>
Learn how to build a script search system for South Park and practice your knowledge on Flows and Pods
</td>
<td><h3>🐣</h3></td>
</tr>

<tr>
<td>
<h4><a href="https://github.com/jina-ai/examples/tree/master/flower-search">Build a Flower Image Search System</a></h4>
Learn how to build an image search system and define you own executors and run them in docker
</td>
<td><h3>🐣</h3></td>
</tr>

<tr>
<td>
<h4><a href="https://github.com/jina-ai/examples/tree/master/tumblr-gif-search">Video Semantic Search in Scale with Prefetching and Sharding</a></h4>
Learn how to increase the performance by using prefetching and sharding
</td>
<td><h3>🕊</h3></td>
</tr>

<tr>
<td>
<h4><a href="https://docs.jina.ai/chapters/remote/main.html">Distribute Your Workflow Remotely</a></h4>
Learn to run Jina on remote instances and distribute your workflow
</td>
<td><h3>🕊</h3></td>
</tr>

<tr>
<td>
<h4><a href="https://docs.jina.ai/chapters/extend/executor.html">Extend Jina by Implementing Your Own Executor</a></h4>
Learn how to implement your own ideas into Jina's plugin
</td>
<td><h3>🕊</h3></td>
</tr>

<tr>
<td>
<h4><a href="https://docs.jina.ai/chapters/hub/main.html">Run Jina Pod via Docker Container</a></h4>
Learn how Jina solves complex dependencies easily with Docker container
</td>
<td><h3>🕊</h3></td>
</tr>

<tr>
<td>
<h4><a href="https://github.com/jina-ai/jina-hub#publish-your-pod-image-to-jina-hub">Share Your Extension with the World</a></h4>
Learn to use Jina Hub and share your extensions with engineers around the globe
</td>
<td><h3>🚀</h3></td>
</tr>

</table>
  

## 文档

<a href="https://docs.jina.ai/">
<img align="right" width="350px" src="https://github.com/jina-ai/jina/blob/master/.github/jina-docs.png?raw=true " />
</a>

要深入学习Jina，最好的方法就是阅读我们的文档。文档建立在主分支的每个推送、合并和发布事件上。你可以在我们的文档中找到关于以下主题的更多细节。

-   [Jina命令行接口参数解释](https://docs.jina.ai/chapters/cli/main.html)
-   [Jina Python API接口](https://docs.jina.ai/api/jina.html)
-   [用于执行器、驱动和流程的Jina YAML语法](https://docs.jina.ai/chapters/yaml/yaml.html)
-   [Jina Protobuf方案](https://docs.jina.ai/chapters/proto/main.html)
-   [Jina中使用的环境变量](https://docs.jina.ai/chapters/envs.html)
-   ..[以及更多](https://docs.jina.ai/index.html)

你是 "文档"明星吗？是的?加入我们吧!我们欢迎大家对文档进行各种改进。

[旧版本的文档在这里存档。](https://github.com/jina-ai/docs/releases).

## 贡献者

我们欢迎来自开源社区、个人和合作伙伴的各种贡献。没有你的积极参与，Jina就不会成功。

下面的资源将帮助你做好第一份贡献。

-   [缴款准则](CONTRIBUTING.md)
-   [释放周期和发展阶段](RELEASE.md)

## 社区

-   [Slack频道](https://join.slack.com/t/jina-ai/shared_invite/zt-dkl7x8p0-rVCv~3Fdc3~Dpwx7T7XG8w) - 为开发者提供交流平台，探讨Jina
-   [社区通讯](mailto:newsletter+subscribe@jina.ai) - 订阅金娜的最新更新、发布和活动消息，订阅金娜的最新动态、发布和活动消息。
-   [LinkedIn](https://www.linkedin.com/company/jinaai/) - 了解Jina AI公司并寻找工作机会
-   ![Twitter Follow](https://img.shields.io/twitter/follow/JinaAI_?label=Follow%20%40JinaAI_&style=social) - 关注我们，并使用tag标签与我们互动`#JinaSearch`  
-   [公司](https://jina.ai) - 了解更多关于我们公司的信息，我们完全致力于开源!

## 路线图

[GitHub的里程碑](https://github.com/jina-ai/jina/milestones)为今后的改进工作铺设了道路。

我们正在寻找合作伙伴，围绕Jina建立一个开放治理模式（如技术指导委员会），以建立一个健康的开源生态系统和开发者友好的文化。如果您有兴趣参与，请随时联系我们，地址是[hello@jina.ai](mailto:hello@jina.ai).

## 许可证

Copyright (c) 2020 Jina AI Limited.保留所有权利。

Jina是在Apache License 2.0版本下授权的。[许可证全文见LICENSE。](LICENSE)